【学术论文】基于深浅特征融合的人脸识别
摘 要 :
针对传统的浅层特征所提取特征的判别性有限、深度特征需要大量带标记样本且训练过程耗时长的问题,提出一种深度及浅层特征融合算法用于人脸识别。首先提取人脸的HOG特征并进行判别性降维;同时,提取人脸图像的PCANet特征并降维;其次,将降维后的深浅特征进行融合,并进一步提取判别性特征;最后,采用SVM分类器进行分类并在AR和Yale B数据库上对算法进行验证。实验结果证明,该算法能够比单独选用深度特征和浅层特征进行分类达到更高的识别率,且对特征维数具有更强的鲁棒性。
中文引用格式: 赵淑欢. 基于深浅特征融合的人脸识别[J].电子技术应用,2020,46(2):28-31,35.
英文引用格式: Zhao Shuhuan. Fusion of deep and shallow features for face recognition[J]. Application of Electronic Technique,2020,46(2):28-31,35.
1.1 浅层特征提取
1.2 深度特征提取
1.3 判别性信息再选取
1.4 特征融合
2.1 AR数据库
2.2 Yale B数据库实验
参考文献
[1] KIRBY M,SIROVICH L.Application of the karhunen-loeve procedure for the characterization of human faces[J].IEEE Transactions on Pattern analysis and Machine intelligence,1990,12(1):103-108.
[2] 首照宇,杨晓帆,莫建文.基于改进的RPCA人脸识别算法[J].电子技术应用,2015,41(9):157-160.
[3] HE X,NIYOGI P.Locality preserving projections[C].Advances in Neural Information Processing Systems,2004:153-160.
[4] QIAO L,CHEN S,TAN X.Sparsity preserving projections with applications to face recognition[J].Pattern Recognition,2010,43(1):331-341.
[5] HE X,CAI D,YAN S,et al.Neighborhood preserving embedding[C].IEEE International Conference on Computer Vision,2005:1208-1213.
[6] QIAO Z,ZHOU L,HUANG J Z.Sparse linear discriminant analysis with applications to high dimensional low sample size data[J].Iaeng International Journal of Applied Mathematics,2009,39(1):48-60.
[7] FAN Z,XU Y,ZHANG D.Local linear discriminant analysis framework using sample neighbors[J].IEEE Transactions on Neural Networks,2011,22(7):1119-1132.
[8] 郝静静,李莉.一种基于KPCA与LDA的人脸识别改进算法[J].电子技术应用,2013,39(12):132-137.
[9] YE J,XIONG T.Null space versus orthogonal linear discriminant analysis[C].International Conference on Machine Learning,2006:1073-1080.
[10] YE J,JANARDAN R,LI Q,et al.Feature reduction via generalized uncorrelated linear discriminant analysis[J].IEEE Transactions on Knowledge and Data Engineering,2006,18(10):1312-1322.
[11] YANG J,ZHANG D,YONG X,et al.Two-dimensional discriminant transform for face recognition[J].Pattern Recognition,2005,38(7):1125-1129.
[12] Wen Jie,Fang Xiaozhao,Cui Jinrong,et al.Robust sparse linear discriminant analysis[J].IEEE Transactions on Circuits and Systems for Video Technology,2019,29(2):390-403.
[13] Zhang Wuming,Zhao Xi,JEAN-MARIE M,et al.Improving shadow suppression for illumination robust face recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,41(3):611-624.
[14] Hu Changhui,Lu Xiaobo,Liu Pan,et al.Single sample face recognition under varying illumination via QRCP decomposition[J].IEEE Transactions on Image Processing,2019,28(5):2624-2638.
[15] Du Lingshuang,Hu Haifeng.Nuclear norm based adapted occlusion dictionary learning for face recognition with occlusion and illumination changes[J].Neurocomputing,2019,340:133-144.
[16] 欧阳宁,钟欢虹,袁华,等.针对光照变化的人脸识别算法研究[J].电子技术应用,2015,41(5):152-155.
[17] BENGIO Y,COURVILLE A,VINCENT P.Representation learning:a review and new perspectives[J].IEEE Transactions on Pattern Analysis and Machine. Intelligence,2013,35(8):1798-1828.
[18] 范叶平,李玉,杨德胜,等.基于深度集成学习的人脸智能反馈认知方法[J].电子技术应用,2019,45(5):5-8.
[19] 黄海新,张东.基于深度学习的人脸活体检测算法[J].电子技术应用,2019,45(8):44-47.
[20] GOODFELLOW I J,WARDE-FARLEY D,MIRZA M,et al.Maxout networks [C].Processing of 30th ICML,2013:1-9.
[21] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural network[C].NIPS,2012:1097-1105.
[22] Li Yong,Zeng Jiabei,Shan Shiguang,et al.Occlusion aware facial expression recognition using CNN with attention mechanism[J].IEEE Transactions on Image Processing,2019,28(5):2439-2450.
[23] SHAKEEL M S,LAM K M.Deep-feature encoding-based discriminative model for age-invariant face recognition[J].Pattern Recognition,2019,93:442-457.
[24] BRUNA J,MALLAT S.Invariant scattering convolution networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(8):1872-1886.
[25] CHAN T H,Jia Kui,Gao Shenghua,et al.PCANet:a simple deep learning baseline for image classification? [J].IEEE Transactions on Image Peocessing,2015,24(12):5017-5032.
作者信息:
赵淑欢
(河北大学 电子信息工程学院,河北 保定071002)
原创声明:此内容为AET网站原创,未经授权禁止转载。